Mistral-7B-0.3_auto
Collection
36 items
•
Updated
Mistral-7B_task-1_60-samples_config-1_auto
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the GaetanMichelet/chat-60_ft_task-1_auto dataset. It achieves the following results on the evaluation set:
- Loss: 0.7895
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0663 | 0.8696 | 5 | 1.0320 |
| 0.887 | 1.9130 | 11 | 0.8524 |
| 0.7166 | 2.9565 | 17 | 0.7895 |
| 0.5246 | 4.0 | 23 | 0.8279 |
| 0.3244 | 4.8696 | 28 | 0.8766 |
| 0.2036 | 5.9130 | 34 | 1.1719 |
| 0.069 | 6.9565 | 40 | 1.2153 |
| 0.0557 | 8.0 | 46 | 1.3490 |
| 0.0301 | 8.8696 | 51 | 1.4461 |
| 0.0269 | 9.9130 | 57 | 1.5283 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 9
Model tree for GaetanMichelet/Mistral-7B_task-1_60-samples_config-1_auto
Base model
mistralai/Mistral-7B-v0.3
Finetuned
mistralai/Mistral-7B-Instruct-v0.3